双目立体视觉技术及其在智慧农业中的应用研究进展  

Research progress on binocular stereo vision technology and its applications in smart agriculture

作　　者：杨学军[1] 钟金彪 林开颜[1] 吴军辉[1] 陈杰[1] 司慧萍[1] YANG Xuejun;ZHONG Jinbiao;LIN Kaiyan;WU Junhui;CHEN Jie;SI Huiping(Modern Agricultural Science and Engineering Institute,Tongji University,Shanghai 201804,China)

机构地区：[1]同济大学现代农业科学与工程研究院,上海201804

出　　处：《农业工程学报》2025年第1期27-39,共13页Transactions of the Chinese Society of Agricultural Engineering

基　　金：上海市科委科技创新行动计划课题(23N21900400)。

摘　　要：双目立体视觉技术作为一种获取现实世界立体感知的重要方法,可以实现农业场景目标的三维定位和点云重建,提取立体三维信息,具有很大的应用潜力。该文介绍了双目立体视觉技术的应用流程,包括双目视觉标定、极线校正、立体匹配等方面,以及相关研究进展;综合近期文献,探讨了双目立体视觉技术在果实定位采摘与地图导航、生长参数测量和病害识别与施药等农业领域最新的应用。综述结果表明,双目立体视觉技术在农业中定位、测量和识别均具有较高精度,但仍面临模型复杂、场景受限、数据集少和立体匹配缺少评价标准等问题。展望该技术在农业领域的未来发展,应着重从算法设计与优化、智能辅助平台搭建、数据集构建和评价体系完善等方面开展研究探索。To achieve precision operations,it is essential to accurately locate targets within agricultural scenes.As an important method for obtaining three-dimensional(3D)perception of the real world,binocular stereo vision technology can facilitate the 3D localization and point cloud reconstruction of targets in agricultural environments,thereby showcasing considerable application potential.This paper conducts an in-depth study of binocular stereo vision technology and its applications in the agricultural field.Firstly,we summarize the pipeline of binocular stereo vision technology,reviewing its latest research advancements along the technical threads of binocular camera calibration,epipolar rectification,and stereo matching.The binocular camera calculates the depth information of targets based on disparity results.The objective of stereo vision calibration is to determine the intrinsic and extrinsic parameters of the camera,establishing a mapping between points in pixel coordinates and world coordinates,which includes reference calibration,active vision calibration,self-calibration,and neural network calibration methods.Epipolar rectification employs constraints to reduce the search space for matching points from two dimensions to one.Stereo matching calculates disparity by matching left and right images in both feature-based and deep learning methods.Feature-based methods can be further categorized into local,global,and semi-global methods,depending on the search range of matching pixels.Local methods search for matching points within surrounding areas,global methods minimize the global energy function,and semi-global methods aggregate costs from various directions.In contrast,deep learning methods can learn more complex features to enhance stereo matching results,further categorized by network frameworks such as convolutional neural networks(CNN),generative adversarial networks(GAN),and transformer methods.In addition,three prominent methods of neural architecture search(NAS)、iterative optimization(IO)and graph neur

关 键 词：双目视觉 智慧农业 立体匹配 作物参数测量 三维目标定位 病害识别 

分 类 号：S126[农业科学—农业基础科学]